Also known as: Self supervised Learning
Self-supervised learning is a machine learning approach that creates training signals from unlabeled data itself. It converts aspects of an unsupervised problem into supervised learning by generating surrogate labels, making it useful when labeled data is scarce but unlabeled data is abundant.
A family of techniques for converting an unsupervised machine learning problem into a supervised machine learning problem by creating surrogate labels from unlabeled examples. Some Transformer-based models such as BERT use self-supervised learning. Self-supervised training is a semi-supervised learning approach.